Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.3648. Min Act: -0.1700
Data Index: 6483489 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.2398. Min Act: -0.1700
Data Index: 6293389 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.2398. Min Act: -0.1700
Data Index: 4179419 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.2085. Min Act: -0.1700
Data Index: 5822509 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.1773. Min Act: -0.1700
Data Index: 2963131 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.1460. Min Act: -0.1700
Data Index: 3477927 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.1460. Min Act: -0.1700
Data Index: 1958242 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.1147. Min Act: -0.1700
Data Index: 5995401 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.0835. Min Act: -0.1700
Data Index: 733535 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.0210. Min Act: -0.1700
Data Index: 6936116 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.0210. Min Act: -0.1700
Data Index: 311867 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.0210. Min Act: -0.1700
Data Index: 7512400 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.0210. Min Act: -0.1700
Data Index: 1966076 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.0210. Min Act: -0.1700
Data Index: 3925614 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3648. Min Range: -4.3648
Max Act: 3.9897. Min Act: -0.1700
Data Index: 5489000 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.0210. Min Act: -0.1700
Data Index: 2040125 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3648. Min Range: -4.3648
Max Act: 3.9897. Min Act: -0.1700
Data Index: 7140184 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3648. Min Range: -4.3648
Max Act: 3.9897. Min Act: -0.1700
Data Index: 1093608 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3648. Min Range: -4.3648
Max Act: 3.9897. Min Act: -0.1700
Data Index: 616553 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3648. Min Range: -4.3648
Max Act: 4.0210. Min Act: -0.1700
Data Index: 4806545 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19